Transfers the labels
TransferData(
anchorset,
refdata,
weight.reduction = "pcaproject",
l2.norm = FALSE,
dims = 1:30,
k.weight = 50,
sd.weight = 1,
eps = 0,
do.cpp = TRUE,
verbose = TRUE,
slot = "data"
)Results from FindTransferAnchors
Data to transfer. Should be either a vector where the names correspond to reference cells, or a matrix, where the column names correspond to the reference cells.
Dimensional reduction to use for the weighting. Options are:
pcaproject: Use the projected PCA used for anchor building
pca: Use an internal PCA on the query only
cca: Use the CCA used for anchor building
custom DimReduc: User provided DimReduc object computed on the query cells
Perform L2 normalization on the cell embeddings after dimensional reduction
Number of PCs to use in the weighting procedure
Number of neighbors to consider when weighting
Controls the bandwidth of the Gaussian kernel for weighting
Error bound on the neighbor finding algorithm (from RANN)
Run cpp code where applicable
Print progress bars and output
Slot to store the imputed data
If refdata is a vector, returns a dataframe with label predictions. If refdata is a matrix, returns an Assay object where the imputed data has been stored in the provided slot.